In [1]:
import util
import os
from IPython.core.display import Markdown
benchmark = 'dodecahedron'
In [2]:
Markdown(open(os.path.join(benchmark, 'README.md'), 'r').read())
Out[2]:

dodecahedron benchmark

The dodecahedron benchmark runs a system of $131,072$ dodecahedra using hard particle Monte Carlo. This is a synthetic benchmark of 3D convex polyhedra performance.

Parameters:

  • $N = 131,072$
  • Hard particle Monte Carlo
    • Vertices: see dodecahdron/bmark.py
    • $d = 0.3$
    • $a = 0.26$
    • $n_\mathrm{select} = 4$

Performance data

Performance results are reported in hours to complete ten million Monte Carlo sweeps, where one sweep is N trial moves.

In [3]:
rows = util.read_rows(benchmark)
table = util.make_table(rows)
Markdown(table)
Out[3]:
Date System Compiler CUDA HOOMD Precision N CPU GPU Ranks Time for 10e6 steps (hours)
2018/01/15 comet gcc 4.9.2 8.0 2.2.2 double 131,072 Intel(R) Xeon(R) CPU E5-2680 v4 @ 2.40GHz Tesla P100-PCIE-16GB 1 7.28
2016/10/23 psg gcc 4.8.5 8.0 2.1.1 double 131,072 Intel(R) Xeon(R) CPU E5-2698 v3 @ 2.30GHz Tesla P100-PCIE-16GB 1 6.22
2016/10/23 psg gcc 4.8.5 8.0 2.1.1 double 131,072 Intel(R) Xeon(R) CPU E5-2698 v3 @ 2.30GHz Tesla M40 24GB 1 17.33
2016/10/23 psg gcc 4.8.5 8.0 2.1.1 double 131,072 Intel(R) Xeon(R) CPU E5-2698 v3 @ 2.30GHz Tesla K80 1 25.66
2016/10/23 psg gcc 4.8.5 8.0 2.1.1 double 131,072 Intel(R) Xeon(R) CPU E5-2698 v3 @ 2.30GHz Tesla K40m 1 30.98
In [4]:
from IPython.display import HTML

#Hide code blocks
HTML('''<script>
code_show=true; 
function code_toggle() {
 if (code_show){
 $('div.input').hide();
 } else {
 $('div.input').show();
 }
 code_show = !code_show
} 
$( document ).ready(code_toggle);
</script>
The raw code for this IPython notebook is by default hidden for easier reading.To toggle on/off the raw code, click <a href="javascript:code_toggle()">here</a>.''')
Out[4]:
The raw code for this IPython notebook is by default hidden for easier reading.To toggle on/off the raw code, click here.
In [ ]: